Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of string-theory terminology (e.g. “string,” “theory,” “Calabi-Yau manifold,” and related physics concepts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     introduced
    -0.06
     ignite
    -0.06
     trabal
    -0.06
     ndarray
    -0.06
    _RA
    -0.06
    >
↵
↵
    -0.06
     CHE
    -0.06
     nrows
    -0.06
    developers
    -0.06
    EFF
    -0.06
    POSITIVE LOGITS
    .swift
    0.07
    string
    0.07
     tinh
    0.06
    сты
    0.06
     extensive
    0.06
    :string
    0.06
    ..\
    0.06
    .Bit
    0.06
    0.06
     Moses
    0.06
    Act Density 0.003%

    No Known Activations